A method for enhancing stability of an aircraft under complex weather

Abstract

The application relates to the field of intelligent control of an aircraft, and discloses an aircraft stability enhancement method under complex weather, which comprises the following steps: acquiring a kth flight state and a k-1th historical disturbance sequence; the kth flight state comprises an actual flight state of the aircraft at a kth moment; the k-1th historical disturbance sequence comprises a plurality of weather disturbances of a complex weather environment associated with a historical moment sequence; the k-1th historical disturbance sequence is processed to obtain a kth predicted disturbance sequence; based on the kth predicted disturbance sequence and the kth flight state, a k+1th control instruction is determined; based on the k+1th control instruction, the aircraft is controlled to be in a k+1th flight state in the complex weather environment at a k+1th moment, so as to improve the stability of the aircraft in the complex weather environment at the k+1th moment. The scheme realizes accurate improvement of the flight stability of the aircraft in the complex weather environment.

Description

Technical Field

[0001] This application relates to the field of intelligent control of aircraft, specifically to, but not limited to, a method for enhancing the stability of aircraft under complex weather conditions. Background Technology

[0002] When aircraft are used in scenarios such as logistics distribution, agricultural plant protection, and emergency rescue, their flight attitude and trajectory are easily affected by complex weather conditions, including rainfall and strong winds. Therefore, under the complex weather conditions of the above scenarios, precise control of the stability of aircraft flight is an important condition for safe flight.

[0003] In practical applications, the control commands for the next moment are typically determined by collecting the meteorological conditions of the complex environment in which the aircraft is currently located, and then controlling the aircraft's flight maneuvers based on these meteorological conditions and the aircraft's current flight attitude. However, this method has a relatively large error in controlling the aircraft's flight attitude and cannot improve the aircraft's flight stability in complex weather environments. Summary of the Invention

[0004] Based on the above technical problems, this application provides a method for enhancing the stability of aircraft under complex weather conditions, which can achieve precise improvement of the flight stability of aircraft in complex weather environments.

[0005] The technical solution provided in this application is as follows: This application provides a method for enhancing aircraft stability under complex weather conditions, including: Obtain the k-th flight state and the (k-1)-th historical disturbance sequence; wherein, the k-th flight state includes the actual flight state of the aircraft at time k; k is an integer greater than 1; the (k-1)-th historical disturbance sequence includes multiple meteorological disturbances associated with the historical time sequence and complex meteorological environments; the historical time sequence includes multiple historical times at time k; the historical time sequence includes time k-1; The (k-1)th historical disturbance sequence is processed to obtain the kth predicted disturbance sequence; wherein, the kth predicted disturbance sequence includes multiple meteorological disturbances in the complex meteorological environment, corresponding to the kth time and future time sequences; the future time sequence includes multiple future times of the kth time; Based on the k-th predicted disturbance sequence and the k-th flight state, determine the (k+1)-th control command; Based on the (k+1)th control command, the flight state of the aircraft in the complex weather environment is controlled at time (k+1) to improve the stability of the aircraft in the complex weather environment at time (k+1).

[0006] The aircraft stability enhancement method under complex weather conditions provided in this application has at least the following beneficial effects: The aircraft stability enhancement method under complex weather conditions provided in this application embodiment acquires the k-th flight state and the (k-1)-th historical disturbance sequence. The k-th flight state includes the actual flight state of the aircraft at time k, while the (k-1)-th historical disturbance sequence includes multiple meteorological disturbances in the complex weather environment associated with the historical time sequence. The historical time sequence includes multiple historical times, including time k-1. Thus, the actual flight state of the aircraft and the meteorological disturbance sequence corresponding to the complex weather environment are tracked and acquired in the time dimension. Furthermore, by processing the (k-1)-th historical disturbance sequence, the k-th predicted disturbance sequence is obtained. The k-th predicted disturbance sequence includes multiple meteorological disturbances in the complex weather environment corresponding to time k and future times. This improves the efficiency of acquiring the k-th predicted disturbance sequence and also enhances the continuity between the k-th predicted disturbance sequence and the (k-1)-th historical disturbance sequence. At the same time, through the k-th predicted disturbance sequence, the aircraft can obtain in advance the complex weather environment within the time period corresponding to time k and multiple future times. On the one hand, based on the k-th predicted disturbance sequence and the k-th flight state, the k+1-th control command is determined, realizing the correlation between the k+1-th control command, the k-th predicted disturbance sequence, and the actual flight state of the aircraft. This improves the targeting of the k+1-th control command and the changing state of meteorological elements in the complex meteorological environment at time k and its multiple future times, thereby improving the accuracy of the k+1-th control command. On this basis, based on the k+1-th control command, the aircraft's k+1-th flight state in the complex meteorological environment is controlled at time k+1 to improve the stability of the aircraft's flight in the complex meteorological environment at time k+1. Thus, in the process of specifically weakening the negative impact of the complex meteorological environment on the aircraft's flight state at time k+1, the k-1-th historical disturbance sequence of the complex meteorological environment is also referenced, thereby enabling precise improvement of the aircraft's flight stability in the complex meteorological environment from the time domain dimension, and thus improving the stability of the aircraft's flight in the complex meteorological environment at time k+1. Attached Figure Description

[0007] Figure 1 A flowchart illustrating the method for enhancing aircraft stability under complex weather conditions provided in this application embodiment. Detailed Implementation

[0008] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0009] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0010] When aircraft are used in scenarios such as logistics distribution, agricultural plant protection, and emergency rescue, their flight attitude and trajectory are easily affected by complex weather conditions, including rainfall and strong winds. Therefore, under the complex weather conditions of the above scenarios, precise control of the stability of aircraft flight is an important condition for safe flight.

[0011] In practical applications, the control commands for the next moment are typically determined by collecting the meteorological conditions of the complex environment in which the aircraft is currently located, and then controlling the aircraft's flight maneuvers based on these meteorological conditions and the aircraft's current flight attitude. However, this method has a relatively large error in controlling the aircraft's flight attitude and cannot improve the aircraft's flight stability in complex weather environments.

[0012] Based on the above technical problems, this application provides a method for enhancing the stability of aircraft under complex weather conditions.

[0013] Figure 1 A flowchart illustrating the method for enhancing aircraft stability under complex weather conditions provided in this application embodiment is shown below. Figure 1 As shown, the method may include the following steps: Step 101: Obtain the k-th flight state and the (k-1)-th historical perturbation sequence.

[0014] Wherein, the k-th flight state includes the actual flight state of the aircraft at time k; k is an integer greater than 1; the (k-1)-th historical disturbance sequence includes multiple meteorological disturbances in complex meteorological environments associated with the historical time sequence; the historical time includes multiple historical times at time k; and the historical time sequence includes time k-1.

[0015] In some embodiments, a complex meteorological environment includes a combination of multiple anomalous meteorological elements or extreme meteorological elements. A complex meteorological environment is a weather and climate state that can have a significant impact on human activities, engineering operations, ecosystems, etc. For example, a complex meteorological environment may include a combination of strong convection, low temperature rain, snow and ice, high temperature and high humidity, sand and dust and haze, and typhoon secondary disaster chains, etc.

[0016] In some embodiments, a complex meteorological environment may include a meteorological environment that has an impact on the stability of aircraft flight that is greater than or equal to a certain threshold.

[0017] In some embodiments, the aircraft may include a drone.

[0018] In some embodiments, meteorological disturbances may include irregular fluctuations or abnormal changes in meteorological elements that deviate from their average state within a complex meteorological environment; for example, meteorological elements may include temperature, air pressure, humidity, and wind.

[0019] In some embodiments, meteorological disturbances can characterize the changes of the above meteorological elements in a historical time series.

[0020] In some embodiments, the number of historical moments in the historical time sequence can be preset or flexibly adjusted, and this application embodiment does not limit this.

[0021] In some embodiments, during the flight of the aircraft, the (k-1)th historical perturbation sequence corresponding to the historical time sequence can be stored in the storage space associated with the aircraft; for example, the (k-1)th historical perturbation sequence can be obtained in any of the following ways: Obtain the (k-1)th historical perturbation sequence from the storage space.

[0022] At multiple historical moments, while the aircraft is in flight, multiple meteorological elements corresponding to complex meteorological environments are measured through a set of sensors associated with the aircraft, thereby obtaining the (k-1)th historical disturbance corresponding to each historical moment.

[0023] In some embodiments, the k-th flight state may include three main categories: basic flight state, attitude state, and mission-related state. The basic flight state may include hovering state, vertical ascent and descent state, horizontal flight state, and hovering state, while the attitude state may include pitching state, hovering state, and roll state. The mission-related state may include fully automatic control state and semi-automatic control state.

[0024] In some embodiments, the k-th flight state can be obtained in the following way: During flight, the aircraft's position, attitude, speed, altitude, and other data are sensed by the onboard sensing system associated with the aircraft to obtain raw sensing data. The raw sensing data is then calculated and integrated to obtain the k-th flight state.

[0025] Step 102: Process the (k-1)th historical perturbation sequence to obtain the kth predicted perturbation sequence.

[0026] Among them, the k-th predicted disturbance sequence includes multiple meteorological disturbances in complex meteorological environments, corresponding to the k-th time and future time sequences; the future time sequence includes multiple future times of the k-th time.

[0027] In some embodiments, the number of future moments included in the future moment sequence can be preset or flexibly adjusted, and this application embodiment does not limit this.

[0028] In some embodiments, the k-th predicted perturbation sequence can be obtained in the following way: The (k-1)th historical perturbation sequence is predicted using a Long Short-Term Memory (LSTM) network to obtain the k-th predicted perturbation sequence. The LSTM can extract the variation pattern of meteorological perturbation in complex meteorological environment from the (k-1)th historical perturbation sequence through the linkage data processing between the input gate, forget gate, cell state update and output gate, and make predictions based on the development trend of the variation pattern to obtain the k-th predicted perturbation sequence.

[0029] Step 103: Based on the k-th predicted disturbance sequence and the k-th flight state, determine the (k+1)-th control command.

[0030] In some embodiments, the (k+1)th control command can be used to control the flight state of the aircraft at time (k+1); exemplaryly, the (k+1)th control command may include at least one indication for controlling the state of the aircraft's motion attitude and / or position changes; exemplaryly, the (k+1)th control command may include adjusting the direction of the aircraft's drive force and / or attitude to counteract or offset the negative impact of meteorological disturbances corresponding to meteorological elements in complex meteorological environments on the flight state of the aircraft.

[0031] Accordingly, the (k+1)th control instruction can be determined in the following way: Based on the k-th predicted disturbance sequence, the meteorological disturbances corresponding to meteorological elements in the complex meteorological environment within the future time period corresponding to the future time period are quantified, and the k-th degree of obstruction of the above meteorological disturbances on the flight state of the aircraft within the future time period is predicted. Then, the k+1-th control command is generated according to the k-th degree of obstruction. For example, if the k-th degree of obstruction represents the obstruction direction and obstruction force of the meteorological elements contained in the complex meteorological environment within the future time period, for example, if the k-th degree of obstruction represents the obstruction of the flight state of the aircraft in the first direction, then the k+1-th control command may include outputting power in the second direction to counteract or resist the obstruction of the meteorological elements on the aircraft in the first direction; wherein, the first direction and the second direction may be opposite.

[0032] Step 104: Based on the (k+1)th control command, control the flight state of the aircraft in the (k+1)th flight state in the complex weather environment at time (k+1)th, so as to improve the stability of the aircraft in the complex weather environment at time (k+1).

[0033] In some embodiments, at time k+1, the aircraft can respond to the control command at time k+1 and control the magnitude and / or direction of its driving force, thereby regulating the flight state of the aircraft in complex weather environments to counteract the negative impact of meteorological elements of complex weather environments on the flight state of the aircraft, thereby improving the stability of the aircraft's flight state.

[0034] As can be seen from the above, the aircraft stability enhancement method under complex weather conditions provided in this application obtains the k-th flight state and the (k-1)-th historical disturbance sequence. The k-th flight state includes the actual flight state of the aircraft at time k, while the (k-1)-th historical disturbance sequence includes multiple meteorological disturbances in the complex weather environment associated with the historical time sequence. The historical time sequence includes multiple historical times, including time k-1. Thus, the actual flight state of the aircraft and the meteorological disturbance sequence corresponding to the complex weather environment are obtained in a tracking manner in the time dimension. Furthermore, by processing the (k-1)-th historical disturbance sequence, the k-th predicted disturbance sequence is obtained. The k-th predicted disturbance sequence includes multiple meteorological disturbances in the complex weather environment corresponding to time k and future times. This improves the efficiency of obtaining the k-th predicted disturbance sequence and also improves the continuity between the k-th predicted disturbance sequence and the (k-1)-th historical disturbance sequence. At the same time, through the k-th predicted disturbance sequence, the aircraft can obtain in advance the complex weather environment within the time period corresponding to time k and multiple future times. On the one hand, based on the k-th predicted disturbance sequence and the k-th flight state, the k+1-th control command is determined, realizing the correlation between the k+1-th control command, the k-th predicted disturbance sequence, and the actual flight state of the aircraft. This improves the targeting of the k+1-th control command and the changing state of meteorological elements in the complex meteorological environment at time k and its multiple future times, thereby improving the continuity and accuracy of the k+1-th control command in the time dimension. On this basis, based on the k+1-th control command, the aircraft's k+1-th flight state in the complex meteorological environment is controlled at time k+1 to improve the stability of the aircraft in the complex meteorological environment at time k+1. Thus, in the process of specifically weakening the negative impact of the complex meteorological environment on the aircraft's flight state at time k+1, the k-1-th historical disturbance sequence of the complex meteorological environment is also referenced, thereby enabling precise improvement of the aircraft's flight stability in the complex meteorological environment from the time domain dimension, and thus improving the stability of the aircraft in the complex meteorological environment at time k+1.

[0035] Based on the foregoing embodiments, the method for enhancing aircraft stability under complex conditions provided in this application, which determines the (k+1)th control command based on the k-th predicted disturbance sequence and the k-th flight state, can be achieved through the following steps: Step A1: Determine the k-th observation disturbance for the aircraft at time k based on the k-th flight state.

[0036] In some embodiments, the kth observed disturbance can characterize the kth disturbance deviation between the disturbance corresponding to the kth flight state and the expected disturbance corresponding to the kth expected state; for example, the kth expected state may include the flight state that the aircraft should have at the kth time, and the kth disturbance deviation may include the disturbance generated by meteorological elements in a complex meteorological environment, and the disturbance effect on at least one dimension of the aircraft's flight direction, flight attitude and flight mode.

[0037] In some embodiments, the k-th observation perturbation can be determined in the following way: Obtain the k-th expected state, determine the k-th state deviation between the k-th expected state and the k-th flight state, convert the k-th state deviation into meteorological disturbance data of meteorological elements in complex meteorological environment for the flight state of the aircraft, and determine the above meteorological disturbance data as the k-th observed disturbance.

[0038] Step A2: Based on the k-th predicted disturbance sequence and the k-th observed disturbance, determine the (k+1)-th control command.

[0039] In some embodiments, the (k+1)th control instruction can be determined in the following way: The sequence of observed disturbance and predicted disturbance at time is analyzed to determine the changing trend of at least one meteorological element in the complex meteorological environment on the flight disturbance of the aircraft. Then, the predicted disturbance at time k+1 is determined based on the changing trend. Based on the direction and / or magnitude represented by the predicted disturbance at time k+1, the k+1 control command is determined. For example, the k+1 control command is used to control the flight maneuver or flight direction of the aircraft to offset or counteract the negative impact of meteorological elements in the complex meteorological environment on the aircraft.

[0040] As can be seen from the above, in the aircraft stability enhancement method under complex weather conditions provided in this application embodiment, the k-th observed disturbance for the aircraft at time k is determined based on the k-th flight state. In this way, by associating the k-th observed disturbance with the k-th flight state, the accuracy and real-time performance of the k-th observed disturbance can be improved. Furthermore, based on the k-th predicted disturbance sequence and the k-th observed disturbance, the k+1-th control command is determined, so that the k+1-th control command can be directly related to the k-th predicted disturbance sequence and the k-th observed disturbance. This allows the k+1-th control command to specifically counteract the impact of the k-th predicted disturbance sequence and the k-th observed disturbance on the aircraft's flight state at time k+1, thereby improving the stability of the aircraft's flight state at time k+1.

[0041] Based on the foregoing embodiments, the method for enhancing aircraft stability under complex conditions provided in this application, which determines the k-th observed disturbance of the aircraft at the k-th moment based on the k-th flight state, can also be implemented through the following steps: Step B1: Determine the k-th state deviation of the aircraft.

[0042] Among them, the deviation of the kth state is at least related to the kth flight state.

[0043] In some embodiments, the k-th state deviation may include the state deviation between the k-th flight state and the k-th expected state; accordingly, the k-th state deviation may be determined in the following manner: The deviation of the k-th state is determined by comparing the k-th flight state with the k-th expected state.

[0044] In some embodiments, the k-th expected state can be determined in the following way: The state transition matrix, the (k-1)th control input matrix, and the disturbance input matrix of the aircraft are obtained, and the (k-1)th observed disturbance is also obtained. Then, based on the state transition matrix, the (k-1)th control input matrix, and the disturbance input matrix, the (k-1)th flight state and the (k-1)th observed disturbance are processed to obtain the k-th expected state; specifically, the k-th expected state... It can be calculated using equation (1): (1) in, This is the (k-1)th flight state. For the (k-1)th observation perturbation, Here is the state transition matrix. This is the (k-1)th control input matrix. The perturbation input matrix is... This refers to the control command from the time preceding the k-th time.

[0045] Correspondingly, the deviation of the k-th state It can be calculated using equation (2): (2) in, This represents the k-th flight state.

[0046] Step B2: Obtain the (k-1)th observation perturbation.

[0047] In some embodiments, the (k-1)th observation disturbance can be pre-stored in the space associated with the aircraft, so that the aircraft controller can obtain the (k-1)th observation disturbance from the space; correspondingly, the (k-1)th observation disturbance can be determined in the same way as the kth observation disturbance.

[0048] Step B3: Based on the observation gain of the aircraft, process the (k-1)th observation disturbance and the kth state deviation to obtain the kth observation disturbance.

[0049] In some embodiments, the observation gain of an aircraft can be a quantitative indicator that characterizes the sensitivity of the aircraft's observation system to changes in the aircraft's state. Specifically, it is used to characterize the magnitude of change in the measured value output by the observation system when the actual state of the aircraft changes by a unit.

[0050] In some embodiments, the observation gain of the aircraft can be predetermined.

[0051] In some embodiments, the k-th observation perturbation can be obtained in the following way: The k-th state deviation is weighted based on the observation gain to obtain the weighted result of the k-th deviation. Then, the weighted result of the k-th deviation and the (k-1)-th state deviation are summed to obtain the k-th observation perturbation; specifically, it can be shown in equation (3): (3) in, For the k-th observation perturbation, For observation gain, This is the weighted result of the k-th deviation.

[0052] As can be seen from the above, in the aircraft stability enhancement method under complex weather conditions provided in this application embodiment, after determining the k-th state deviation and the (k-1)-th observation disturbance of the aircraft, the (k-1)-th observation disturbance and the k-th state deviation are processed based on the observation gain of the aircraft to obtain the k-th observation disturbance. Thus, by associating the k-th observation disturbance with the k-th state deviation and the (k-1)-th observation disturbance through the above processing flow, the continuity between the k-th and (k-1)-th observation disturbances can be improved, reducing the probability of observation disturbance jumps or errors; furthermore, by associating the k-th observation disturbance with the k-th state deviation, the accuracy of the k-th observation disturbance can also be improved.

[0053] Based on the foregoing embodiments, the method for enhancing aircraft stability under complex conditions provided in this application, which determines the k-th observed disturbance of the aircraft at the k-th moment based on the k-th flight state, can also be achieved through the following steps: Step C1: Determine the k-th state deviation and the (k-1)-th observation disturbance of the aircraft.

[0054] Among them, the deviation of the kth state is at least related to the kth flight state.

[0055] Step C2: Determine the gradient of the kth meteorological disturbance at time k relative to the k-1 historical disturbance sequence.

[0056] In some embodiments, the k-th meteorological disturbance may include meteorological elements of the complex meteorological environment at time k and the degree of disturbance to the k-th flight state of the aircraft; accordingly, the k-th meteorological disturbance can be determined in the following ways: At time k, the raw meteorological data of the kth time is collected by the meteorological sensor associated with the aircraft. Noise and redundant data in the raw meteorological data of the kth time are removed to obtain the meteorological data of the kth time. Then, the degree of disturbance represented by the meteorological data of the kth time is quantified to obtain the meteorological disturbance of the kth time.

[0057] In some embodiments, the k-th gradient of change may include the degree of change of the k-th meteorological disturbance relative to the historical disturbances in the (k-1)-th historical disturbance sequence; accordingly, the k-th gradient of change may be determined in the following manner: In the time dimension, statistics are performed on the k-th meteorological disturbance and the (k-1)-th historical disturbance sequence to obtain the change process of the meteorological disturbance within the historical time period covered by the historical time sequence up to the k-th time. Then, based on the above historical time period up to the k-th time, the change process of the meteorological disturbance is differentiated to obtain the k-th change gradient.

[0058] In some embodiments, the k-th gradient can characterize the gradient of turbulence intensity change in a complex meteorological environment over a period from a historical time period to time k; exemplarily, the k-th gradient... It can be calculated using equation (4): (4) in, It can characterize the k-th meteorological disturbance. It can be the (k-1)th meteorological disturbance in the (k-1)th historical disturbance sequence corresponding to the (k-1)th time. This is the time interval between time k and time (k-1).

[0059] Step C3: If the k-th gradient is greater than or equal to the gradient threshold, increase the observation frequency of the spacecraft.

[0060] Accordingly, if the k-th gradient is less than the gradient threshold, then the operation of increasing the observation frequency of the spacecraft can be omitted.

[0061] For example, if the kth change gradient is less than the gradient threshold, the k-1th observation disturbance and the kth state deviation can be processed directly based on the observation gain of the aircraft using the method provided in the aforementioned embodiments to obtain the kth observation disturbance.

[0062] In some embodiments, the gradient threshold may be predetermined or adjusted; for example, the gradient threshold may be 0.5.

[0063] In some embodiments, the observation frequency may include the number of times the observation gain of the aircraft is recursively calculated to finally obtain the k-th observation perturbation within the observation period; for example, when the k-th change gradient is less than the gradient threshold, the (k-1)-th observation perturbation and the k-th state deviation are processed directly based on the observation gain of the aircraft, and the observation frequency corresponding to the k-th observation perturbation can be the default observation frequency of the aircraft; for example, the default observation frequency can be set as a first frequency; for example, the observation period may include the period between the k-th time and the (k+1)-th time.

[0064] In some embodiments, increasing the observation frequency of the aircraft may include increasing the first frequency to a second frequency; for example, the second frequency may be an integer multiple of the first frequency.

[0065] Step C4: Based on the improved observation frequency, the observation gain of the aircraft, the (k-1)th observation disturbance, and the kth state deviation, determine the kth observation disturbance.

[0066] In some embodiments, the kth observation perturbation can be calculated in the following way: During the observation period, based on the observation gain of the aircraft, the disturbance intensity and state deviation corresponding to different meteorological elements in the (k-1)th observation disturbance are calculated according to the number of calculations indicated by the improved observation frequency. The amplitude set of the kth disturbance element is then statistically averaged to obtain the kth observation disturbance. For example, the amplitude of the disturbance element in the amplitude set of the kth disturbance element can characterize the disturbance amplitude corresponding to the element in different meteorological elements.

[0067] As can be seen from the above, in the method for enhancing aircraft stability under complex weather conditions provided in this application embodiment, after determining the k-th state deviation and the (k-1)-th observation disturbance of the aircraft, the k-th change gradient of the k-th meteorological disturbance at time k relative to the (k-1)-th historical disturbance sequence is determined. In this way, real-time tracking of the k-th state deviation and the k-th change gradient can be achieved. Furthermore, if the k-th change gradient is greater than or equal to the gradient threshold, the observation frequency of the aircraft is increased, and the k-th observation disturbance is determined based on the increased observation frequency, the observation gain of the aircraft, the (k-1)-th observation disturbance, and the k-th state deviation. In this way, the redundancy of the k-th observation disturbance can be reduced, and the disturbance state of meteorological elements on the aircraft in complex weather environments can be displayed more finely with smaller granularity, thereby improving the accuracy of the k-th observation disturbance.

[0068] Based on the foregoing embodiments, in the aircraft stability enhancement method under complex conditions provided in this application, the determination of the k-th observation disturbance based on the improved observation frequency, the aircraft's observation gain, the (k-1)-th observation disturbance, and the k-th state deviation can be achieved in the following way: During the observation period, based on the observation gain of the aircraft, the (k-1)th observation disturbance and the kth state deviation are processed to obtain the first temporary disturbance of the kth observation. Based on the observation gain, the (m-1)th temporary disturbance and the kth state deviation of the kth observation are processed to obtain the mth temporary disturbance of the kth observation. Based on the observation gain, the Mth temporary disturbance and the kth state deviation of the kth observation are processed to obtain the kth observation disturbance.

[0069] Where m is an integer greater than or equal to 1 and less than or equal to M, and M is greater than 1 and is used to characterize the number of observations corresponding to the improved observation frequency.

[0070] In some embodiments, the first temporary perturbation of the k-th observation It can be calculated using equation (5): (5) Correspondingly, the m-th temporary perturbation of the k-th observation It can be calculated using equation (6): (6) in, This is the (m-1)th temporary perturbation in the k-th observation.

[0071] Accordingly, the k-th observation disturbance can be calculated using equation (7): (7) As can be seen from the above, in the aircraft stability enhancement method under complex weather conditions provided in this application embodiment, during the observation period, based on the aircraft's observation gain, the (k-1)th observation disturbance and the kth state deviation are processed to obtain the first temporary disturbance of the kth observation. Based on the observation gain, the (m-1)th temporary disturbance and the kth state deviation of the kth observation are processed to obtain the mth temporary disturbance of the kth observation. Based on the observation gain, the Mth temporary disturbance and the kth state deviation of the kth observation are processed to obtain the kth observation disturbance. Thus, by means of the above process, the recursive calculation of the (k-1)th observation disturbance, the kth state deviation, and the mth temporary disturbance of the kth observation is realized, thereby enabling more precise tracking of subtle changes in the kth state deviation and the kth observation disturbance, and improving the accuracy of the kth observation disturbance.

[0072] Based on the foregoing embodiments, the method for enhancing aircraft stability under complex conditions provided in this application, which determines the (k+1)th control command based on the k-th predicted disturbance sequence and the k-th observed disturbance, can be implemented through the following steps: Step D1: Determine the k-th weight set.

[0073] In some embodiments, the k-th weight set may include a set of weights used to weight the k-th predicted perturbation sequence and the k-th observed perturbation; accordingly, the k-th weight set may be determined in the following manner: In the time dimension, the difference between the k-th predicted perturbation sequence and the k-th observed perturbation is statistically averaged to obtain the k-th statistical result. Then, the k-th prediction deviation between the perturbation in the k-th predicted perturbation sequence and the k-th statistical result is determined, and the k-th observation deviation between the k-th observed perturbation and the k-th statistical result is determined. Then, the k-th prediction deviation and the k-th observation deviation are normalized respectively to obtain the k-th weight set.

[0074] Step D2: Process the k-th predicted perturbation sequence and the k-th observed perturbation based on the k-th weight set to obtain the k-th reference perturbation sequence.

[0075] In some embodiments, if the k-th weight set includes ( Then, the k-th reference perturbation sequence It can be calculated using equation (8): (8) in, Let i be the i-th predicted perturbation in the k-th predicted perturbation sequence, where i is an integer greater than or equal to 1.

[0076] Step D3: Process the k-th reference disturbance sequence and the k-th control command through the aircraft's MPC to obtain the (k+1)-th predicted state set.

[0077] In some embodiments, the (k+1)th predicted state set can be obtained in the following way: Obtain the state transition matrix, the (k-1)th control input matrix, and the disturbance input matrix of the aircraft, obtain the (k-1)th observed disturbance, and then process the k-th flight state and the k-th reference disturbance sequence based on the state transition matrix, the (k-1)th control input matrix, and the disturbance data matrix using the MPC model predictive control algorithm to obtain the (k+1)th predicted state set; specifically as shown in equation (9): (9) in, For the i-th predicted state in the (k+1)-th predicted state set, This is the i-th intermediate predicted state obtained by using equation (9) with the k-th flight state as the initial state. This is the predictive control input at time k+i, corresponding to the initial state of flight k.

[0078] Step D4: Based on the (k+1)th predicted state set and the (k+1)th reference state of the aircraft, determine the (k+1)th control command.

[0079] In some embodiments, the (k+1)th control instruction can be determined in the following way: The state deviation between the (k+1)th predicted state set and the (k+1)th reference state of the aircraft is calculated using the aircraft's objective function. The control command is then adjusted based on the state deviation. Finally, the adjusted control command corresponding to the minimum state deviation is determined as the (k+1)th control command. Specifically, it can be shown in Equation (10): (10) in, Let (Q, R, S) be the minimum value of the objective function, and let (Q, R, S) be the state weight matrix, control input weight matrix, and control increment weight matrix, respectively. These matrices can be predetermined or adjusted.

[0080] Specifically, Used to represent and Minimize the computational process between these parameters, and adjust the tracking accuracy using Q. This is used to represent minimizing the control input energy, and through regulation and constraints using R, to reduce the probability of over-control. To control the increment, it is used to limit the control amplitude corresponding to the control command.

[0081] As can be seen from the above, in the aircraft stability enhancement method under complex weather conditions provided in this application embodiment, the k-th predicted disturbance sequence and the k-th observed disturbance are determined and processed based on the k-th weight set to obtain the k-th reference disturbance sequence. This improves the correlation between the k-th reference disturbance sequence, the k-th predicted disturbance sequence, and the k-th observed disturbance, thereby improving the accuracy of the k-th reference disturbance sequence. Furthermore, the k-th reference disturbance sequence and the k-th control command are processed by the aircraft's MPC to obtain the (k+1)-th predicted state set. This enables comprehensive and accurate prediction of the (k+1)-th predicted state set. Based on this, the (k+1)-th control command is determined based on the (k+1)-th predicted state set and the aircraft's (k+1)-th reference state, which improves the accuracy of the (k+1)-th control command.

[0082] Based on the foregoing embodiments, in the aircraft stability enhancement method under complex conditions provided in this application, determining the k-th weight set can be achieved in the following way: The k-th weight set is determined based on the target factors.

[0083] The target factors include at least one of the following: the data redundancy of the (k-1)th historical perturbation sequence and the confidence of the kth predicted perturbation sequence.

[0084] In some embodiments, the data redundancy of the (k-1)th historical perturbation sequence may include the signal-to-noise ratio and data integrity of the data in the (k-1)th historical perturbation sequence; accordingly, the k-th weight set is determined based on the above redundancy, which can be achieved in the following way: The weights in the k-th weight set that are related to the k-th predicted perturbation sequence decrease as the data redundancy in the (k-1)-th historical perturbation sequence increases; the weights in the k-th weight set that are related to the k-th observed perturbation increase as the aforementioned data redundancy increases.

[0085] In some embodiments, the confidence level of the k-th predicted perturbation sequence can characterize the reliability of the perturbation data in the k-th predicted perturbation sequence; for example, the k-th weight set can be determined in the following manner: The weights in the k-th weight set that are associated with the k-th predicted perturbation sequence increase as the confidence level of the k-th predicted perturbation sequence increases, while the weights in the k-th weight set that are associated with the k-th observed perturbation decrease as the confidence level increases.

[0086] In some embodiments, the k-th weight set can also be determined in the following way: If the data redundancy of the (k-1)th historical perturbation sequence is less than or equal to the redundancy threshold, the weights in the kth weight set that are related to the kth predicted perturbation sequence are determined and increase as the confidence level increases.

[0087] For example, the weights in the k-th weight set can be calculated using equation (11): (11) in, The normalization constant is For example, the k-th moderating factor associated with the target factor; It can increase with the confidence level of the k-th predicted perturbation sequence, and decrease with the increase of data redundancy in the (k-1)-th historical perturbation sequence.

[0088] As can be seen from the above, in the aircraft stability enhancement method under complex weather conditions provided in this application embodiment, a k-th weight set is determined based on at least one of the target factors, including the data redundancy of the (k-1)-th historical disturbance sequence and the confidence level of the k-th predicted disturbance sequence. This allows the weights in the k-th weight set to be correlated with the data redundancy of the (k-1)-th historical disturbance sequence and the confidence level of the k-th predicted disturbance data, thereby improving the dynamics and specificity of the weights in the k-th weight set and increasing their accuracy.

[0089] Based on the foregoing embodiments, in the aircraft stability enhancement method under complex conditions provided in this application, the k-th weight set includes the k-th predicted weights associated with the k-th predicted disturbance sequence and the k-th observed weights associated with the k-th observed disturbance; correspondingly, the k-th weight set can be determined in the following ways: The k-th prediction weight is determined to decrease as the fluctuation of meteorological disturbance in the (k-1)-th historical disturbance sequence increases, and the k-th observation weight is determined to decrease as the k-th prediction weight increases.

[0090] In some embodiments, the k-th prediction weight may include weights in the k-th weight set that are associated with the k-th prediction perturbation sequence; for example, the k-th prediction weight may be one of the weights in the foregoing embodiments. .

[0091] In some embodiments, the k-th observation weight may include weights in the k-th weight set that are related to the k-th observation perturbation; for example, the k-th observation weight may be the weights from the set 1- in the foregoing embodiments. .

[0092] In some embodiments, the degree of fluctuation of meteorological disturbances in the (k-1)th historical disturbance sequence can characterize the magnitude and / or rate of change of meteorological disturbances in the (k-1)th historical disturbance sequence.

[0093] In some embodiments, the adjustment factors in the adjustment factor set may decrease as the volatility of the meteorological disturbance in the (k-1)th historical disturbance sequence increases; exemplarily, the adjustment factors may include For example, after determining the correlation between the adjustment factors in the adjustment factor set and the volatility of meteorological disturbances in the (k-1)th historical disturbance sequence, the following can be determined based on the correlation and the volatility of meteorological disturbances in the (k-1)th historical disturbance sequence: Then, the kth predicted weight in the kth weight set is calculated by equation (11).

[0094] In some embodiments, the sum of the k-th observation weight and the k-th prediction weight can be 1. Thus, after determining the k-th prediction weight, the difference between 1 and the k-th prediction weight can be determined as the k-th observation weight.

[0095] As can be seen from the above, in the aircraft stability enhancement method under complex weather conditions provided in this application embodiment, the k-th weight set includes the k-th prediction weight and the k-th observation weight. It is determined that the k-th prediction weight decreases as the fluctuation degree of the weather disturbance in the (k-1)-th historical disturbance sequence increases, and at the same time, it is determined that the k-th observation weight decreases as the k-th prediction weight increases. In this way, by associating the fluctuation degree of the weather disturbance in the (k-1)-th historical disturbance sequence with the weights in the k-th weight set, the weights in the k-th weight set can reflect the changing state of the weather disturbance in the (k-1)-th historical disturbance sequence, thereby improving the dynamics, real-time performance, and accuracy of the k-th prediction weight and the k-th observation weight in the k-th weight set.

[0096] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0097] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined to obtain new method embodiments without conflict.

[0098] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0099] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0100] It should be noted that the aforementioned computer-readable storage media can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various electronic devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0101] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0102] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0103] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware nodes. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0104] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for enhancing aircraft stability under complex weather conditions, characterized in that, The method includes: Obtain the k-th flight state and the (k-1)-th historical disturbance sequence; wherein, the k-th flight state includes the actual flight state of the aircraft at time k; k is an integer greater than 1; the (k-1)-th historical disturbance sequence includes multiple meteorological disturbances associated with the historical time sequence and complex meteorological environments; the historical time sequence includes multiple historical times at time k; the historical time sequence includes time k-1; The (k-1)th historical disturbance sequence is processed to obtain the kth predicted disturbance sequence; wherein, the kth predicted disturbance sequence includes multiple meteorological disturbances in the complex meteorological environment, corresponding to the kth time and future time sequences; the future time sequence includes multiple future times of the kth time; Based on the k-th predicted disturbance sequence and the k-th flight state, determine the (k+1)-th control command; Based on the (k+1)th control command, the flight state of the aircraft in the complex weather environment is controlled at time (k+1) to improve the stability of the aircraft in the complex weather environment at time (k+1).

2. The method according to claim 1, characterized in that, The determination of the (k+1)th control command based on the k-th predicted disturbance sequence and the k-th flight state includes: Based on the k-th flight state, determine the k-th observation disturbance for the aircraft at the k-th time; Based on the k-th predicted perturbation sequence and the k-th observed perturbation, the (k+1)-th control command is determined.

3. The method according to claim 2, characterized in that, The determination of the k-th observation disturbance for the aircraft at the k-th time based on the k-th flight state includes: Determine the k-th state deviation of the aircraft; wherein the k-th state deviation is at least associated with the k-th flight state; Obtain the (k-1)th observation perturbation; Based on the observation gain of the aircraft, the (k-1)th observation disturbance and the kth state deviation are processed to obtain the kth observation disturbance.

4. The method according to claim 2, characterized in that, The determination of the k-th observation disturbance for the aircraft at the k-th time based on the k-th flight state includes: Determine the k-th state deviation and the (k-1)-th observation disturbance of the aircraft; wherein the k-th state deviation is at least associated with the k-th flight state; Determine the gradient of the k-th meteorological disturbance at time k relative to the (k-1)-th historical disturbance sequence; If the kth gradient change is greater than or equal to the gradient threshold, increase the observation frequency of the aircraft. The k-th observation disturbance is determined based on the improved observation frequency, the observation gain of the aircraft, the (k-1)-th observation disturbance, and the k-th state deviation.

5. The method according to claim 4, characterized in that, The determination of the k-th observation disturbance based on the improved observation frequency, the observation gain of the aircraft, the (k-1)-th observation disturbance, and the k-th state deviation includes: During the observation period, based on the observation gain of the aircraft, the (k-1)th observation disturbance and the kth state deviation are processed to obtain the first temporary disturbance of the kth observation. Based on the observation gain, the (m-1)th temporary disturbance and the kth state deviation of the kth observation are processed to obtain the mth temporary disturbance of the kth observation. Based on the observation gain, the Mth temporary disturbance and the kth state deviation of the kth observation are processed to obtain the kth observation disturbance. Wherein, m is an integer greater than 1 and less than or equal to M, and M is greater than 1 and is used to characterize the number of observations corresponding to the improved observation frequency.

6. The method according to claim 2, characterized in that, The determination of the (k+1)th control command based on the k-th predicted perturbation sequence and the k-th observed perturbation includes: Determine the k-th weight set; Based on the k-th weight set, the k-th predicted perturbation sequence and the k-th observed perturbation are processed to obtain the k-th reference perturbation sequence; The aircraft's MPC processes the k-th reference disturbance sequence and the k-th control command to obtain the (k+1)-th predicted state set. The (k+1)th control command is determined based on the (k+1)th predicted state set and the (k+1)th reference state of the aircraft.

7. The method according to claim 6, characterized in that, Determining the k-th weight set includes: The k-th weight set is determined based on target factors; wherein the target factors include at least one of the following: the data redundancy of the (k-1)-th historical perturbation sequence and the confidence level of the k-th predicted perturbation sequence.

8. The method according to claim 6, characterized in that, The k-th weight set includes the k-th predicted weights associated with the k-th predicted perturbation sequence and the k-th observed weights associated with the k-th observed perturbation; determining the k-th weight set includes: It is determined that the k-th prediction weight decreases as the fluctuation of meteorological disturbance in the (k-1)-th historical disturbance sequence increases, and the k-th observation weight decreases as the k-th prediction weight increases.

Images